INDEX

Explanations

questions related to uncertainty and the need for clarification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enterOuterAlt

-0.71

usercontent

-0.61

Obrázky

-0.58

الدراسه

-0.57

 neceff

-0.53

 Photocase

-0.52

 Lone

-0.51

ApiProperty

-0.50

graphe

-0.50

 resourceCulture

-0.50

POSITIVE LOGITS

 lenker

0.63

GNUC

0.59

depends

0.56

 mystère

0.54

 vraag

0.52

 questão

0.52

 débat

0.51

 question

0.50

లాలు

0.49

Depends

0.49

Activations Density 0.303%

questions related to uncertainty and the need for clarification

No Comments

No Known Activations